Cross-covariance regularized autoencoders for nonredundant sparse feature representation

doi:10.1016/j.neucom.2018.07.050

HFCAS OpenIR

	Cross-covariance regularized autoencoders for nonredundant sparse feature representation
	Chen, Jie 1,2; Wu, ZhongCheng1,3 ; Zhang, Jun1 ; Li, Fang1 ; Li, WenJing 1; Wu, ZiHeng 1
	2018-11-17
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
通讯作者	Chen, Jie(cj2016@mail.ustc.edu.cn)
摘要	We propose a new feature representation algorithm using cross-covariance in the context of deep learning. Existing feature representation algorithms based on the sparse autoencoder and nonnegativity-constrained autoencoder tend to produce duplicative encoding and decoding receptive fields, which leads to feature redundancy and overfitting. We propose using the cross-covariance to regularize the feature weight vector to construct a new objective function to eliminate feature redundancy and reduce overfitting. The results from the MNIST handwritten digits dataset, the NORB normalized-uniform dataset and the Yale face dataset indicate that relative to other algorithms based on the conventional sparse autoencoder and nonnegativity-constrained autoencoder, our method can effectively eliminate feature redundancy, extract more distinctive features, and improve sparsity and reconstruction quality. Furthermore, this method improves the image classification performance and reduces the overfitting of conventional networks without adding more computational time. (C) 2018 Elsevier B.V. All rights reserved.
关键词	Autoencoder Cross-covariance Deep learning Feature representation Receptive fields
DOI	10.1016/j.neucom.2018.07.050
关键词[WOS]	FEATURE-EXTRACTION ; NEURAL-NETWORKS ; NONNEGATIVITY CONSTRAINTS ; DENOISING AUTOENCODERS ; DEEP ; RECOGNITION ; ALGORITHM
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000443971900006
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/38791
专题	中国科学院合肥物质科学研究院
通讯作者	Chen, Jie
作者单位	1.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei, Anhui, Peoples R China 2.Univ Sci & Technol China, Grad Sch Comp Appl Technol, Hefei, Anhui, Peoples R China 3.Univ Sci & Technol China, Hefei, Anhui, Peoples R China
推荐引用方式 GB/T 7714	Chen, Jie,Wu, ZhongCheng,Zhang, Jun,et al. Cross-covariance regularized autoencoders for nonredundant sparse feature representation[J]. NEUROCOMPUTING,2018,316:49-58.
APA	Chen, Jie,Wu, ZhongCheng,Zhang, Jun,Li, Fang,Li, WenJing,&Wu, ZiHeng.(2018).Cross-covariance regularized autoencoders for nonredundant sparse feature representation.NEUROCOMPUTING,316,49-58.
MLA	Chen, Jie,et al."Cross-covariance regularized autoencoders for nonredundant sparse feature representation".NEUROCOMPUTING 316(2018):49-58.